<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-finetuned-material-synthesis
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2542
- Precision: 0.4251
- Recall: 0.5397
- F1: 0.4756
- Accuracy: 0.6519
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 160
- eval_batch_size: 160
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 10 | 2.1424 | 0.0513 | 0.0080 | 0.0138 | 0.4117 |
No log | 2.0 | 20 | 1.7693 | 0.2459 | 0.2745 | 0.2594 | 0.5216 |
No log | 3.0 | 30 | 1.6469 | 0.2973 | 0.3609 | 0.3260 | 0.5469 |
No log | 4.0 | 40 | 1.5164 | 0.3391 | 0.4121 | 0.3720 | 0.5859 |
No log | 5.0 | 50 | 1.4196 | 0.3833 | 0.4856 | 0.4284 | 0.6113 |
No log | 6.0 | 60 | 1.3538 | 0.3974 | 0.4872 | 0.4377 | 0.6272 |
No log | 7.0 | 70 | 1.3072 | 0.4105 | 0.5327 | 0.4637 | 0.6394 |
No log | 8.0 | 80 | 1.2785 | 0.4189 | 0.5180 | 0.4632 | 0.6470 |
No log | 9.0 | 90 | 1.2657 | 0.4170 | 0.5169 | 0.4616 | 0.6476 |
No log | 10.0 | 100 | 1.2542 | 0.4251 | 0.5397 | 0.4756 | 0.6519 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2